Fig 3 - uploaded by Gang Xu
Content may be subject to copyright.
![(a) shows the diagram of cylindrical projection, and (b) is the top view of (a).The core of cylindrical projection transformation is the cylindrical transformation formula [10], and the formula to project image on a cylindrical coordinate is as follows:](profile/Gang-Xu-6/publication/303924471/figure/fig5/AS:668713141428226@1536445045652/a-shows-the-diagram-of-cylindrical-projection-and-b-is-the-top-view-of-aThe-core.png)
(a) shows the diagram of cylindrical projection, and (b) is the top view of (a).The core of cylindrical projection transformation is the cylindrical transformation formula [10], and the formula to project image on a cylindrical coordinate is as follows:
Source publication
Panoramic stitching technology is the focus of current panoramic technology, and cylindrical panoramas are commonly used because of their ease of capture and storage. Moreover it is a simple method for constructing panoramic video. This paper presents a cylindrical panoramic generation method based on multi-cameras. First, we use a backward-divisio...
Citations
... Employing the cylindrical model [40] method, we generate a panoramic image by calculating displacements, converting to a cylindrical coordinate system, and merging the overlapping sections to accurately reconstruct the internal thread's appearance. This study leverages cylindrical mapping technology to ensure seamless image stitching, utilizing the SIFT algorithm for feature detection and the RANSAC algorithm for feature point optimization. ...
In the realm of industrial inspection, the precise assessment of internal thread quality is crucial for ensuring mechanical integrity and safety. However, challenges such as limited internal space, inadequate lighting, and complex geometry significantly hinder high-precision inspection. In this study, we propose an innovative automated internal thread detection scheme based on machine vision, aimed at addressing the time-consuming and inefficient issues of traditional manual inspection methods. Compared with other existing technologies, this research significantly improves the speed of internal thread image acquisition through the optimization of lighting and image capturing devices. To effectively tackle the challenge of image stitching for complex thread textures, an internal thread image stitching technique based on a cylindrical model is proposed, generating a full-view thread image. The use of the YOLOv8 model for precise defect localization in threads enhances the accuracy and efficiency of detection. This system provides an efficient and intuitive artificial intelligence solution for detecting surface defects on geometric bodies in confined spaces.
... With the rapid development of image stitching and image fusion technologies, methods for obtaining multi-view or even global perspectives through multiple single viewpoints have been widely applied in human production and daily life [1][2][3][4][5]. For instance, the extensive use of technologies such as panoramic images, autonomous driving, and virtual reality (VR) enables precise remote observation of scenes by individuals [6][7][8][9]. ...
Image stitching is a crucial aspect of image processing. However, factors like perspective and environment often lead to irregular shapes in stitched images. Cropping or completion methods typically result in substantial loss of information. This paper proposes a method for rectifying irregularly images into rectangles using deformable meshes and residual networks. The method utilizes a convolutional neural network to quantify rigid structures of images. Choosing the most suitable mesh structure based on the extraction results, offering options such as triangular, rectangular, and hexagonal. Subsequently, the irregularly image, predefined mesh structure, and predicted mesh structure are input into a wide residual neural network for regression. The loss function comprises local and global, aimed at minimizing the loss of image information within the mesh and global target. This method not only significantly reduces information loss during rectification but also adapting to different images with various rigid structures. Validation on the DIR-D dataset shows this method outperforms state-of-the-art methods in image rectification.
... With the rapid development of image stitching and image fusion technologies, methods for obtaining multi-view or even global perspectives through multiple single viewpoints have been widely applied in human production and daily life [1][2][3][4][5]. For instance, the extensive use of technologies such as panoramic images, autonomous driving, and virtual reality (VR) enables precise remote observation of scenes by individuals [6][7][8][9]. ...
Image stitching is a crucial aspect of image processing. However, factors like perspective and environment often lead to irregular shapes in stitched images. Cropping or completion methods typically result in substantial loss of information. This paper proposes a method for rectifying irregularly images into rectangles using deformable meshes and residual networks. The method utilizes a convolutional neural network to quantify rigid structures of images. Choosing the most suitable mesh structure based on the extraction results, offering options such as triangular, rectangular, and hexagonal. Subsequently, the irregularly image, predefined mesh structure, and predicted mesh structure are input into a wide residual neural network for regression. The loss function comprises local and global, aimed at minimizing the loss of image information within the mesh and global target. This method not only significantly reduces information loss during rectification but also adapting to different images with various rigid structures. Validation on the DIR-D dataset shows this method outperforms state-of-the-art methods in image rectification.
... Even so, there are usually parts of the environment that are seen from two cameras, due to an overlap between their horizontal fields of view. For specific situations where the cameras are in close proximity to each other, methods such as imagestitching can be used to form a large panoramic image composed of images from several cameras [9,19,20]. Also, new architectures that take as input a number of images and fuse their information internally have been introduced [21,22]. In a more general approach, this problem is often solved through the use of agent re-identification networks, which get rid of redundant detections based on feature similarities [8,23]. ...
The growing on-board processing capabilities have led to more complex sensor configurations, enabling autonomous car prototypes to expand their operational scope. Nowadays, the joint use of LiDAR data and multiple cameras is almost a standard and poses new challenges for existing multi-modal perception pipelines, such as dealing with contradictory or redundant detections caused by inference on overlapping images. In this paper, we address this last issue in the context of sequential schemes like F-PointNets, where object candidates are obtained in the image space, and the final 3D bounding box is then inferred from point cloud information. To this end, we propose the inclusion of a re-identification branch into the 2D detector, i.e., Faster R-CNN, so that objects seen from adjacent cameras can be handled before the 3D box estimation takes place, removing duplicates and completing the object’s cloud. Extensive experimental evaluations covering both the 2D and 3D domains affirm the effectiveness of the suggested methodology. The findings indicate that our approach outperforms conventional Non-Maximum Suppression (NMS) methods. Particularly, we observed a significant gain of over 5% in terms of accuracy for cars in camera overlap regions. These results highlight the potential of our upgraded detection and re-identification system in practical scenarios for autonomous driving.
... However, both the ideal and rigorous panoramic imaging models are developed without consideration of the varied object-distance information in a scene. Lin [30] tries to estimate a unified cylinder projection radius based on a loss function to minimize the projection error of the whole scene. Due to difficulties in fitting a regular cylinder surface for a real environment, stitching errors may still appear where the projection radius departs from the object-distance information. ...
... However, both the ideal and rigorous panoramic ima models are developed without consideration of the varied object-distance informati a scene. Lin [30] tries to estimate a unified cylinder projection radius based on a loss tion to minimize the projection error of the whole scene. Due to difficulties in fitt regular cylinder surface for a real environment, stitching errors may still appear w the projection radius departs from the object-distance information. ...
Panoramic imagery from multi-camera systems often suffers the problem of geometric mosaicking errors due to eccentric errors between the optical centers of cameras and variations in object-distances within the panoramic environment. In this paper, an inverse rigorous panoramic imaging model was derived completely for a panoramic multi-camera system. Additionally, we present an estimation scheme aimed at extracting object-distance information to enhance the seamlessness of panoramic image stitching. The essence of the scheme centers around our proposed object-space-based image matching algorithm called the Panoramic Vertical Line Locus (PVLL). As a result, panoramas were generated using the proposed inverse multi-cylinder projection method, utilizing the estimated object-distance information. The experiments conducted on our developed multi-camera system demonstrate that the root mean square errors (RMSEs) in the overlapping areas of panoramic images are no more than 1.0 pixel. In contrast, the RMSEs of the conventional traditional methods are typically more than 6 pixels, and in some cases, even exceed 30 pixels. Moreover, the inverse imaging model has successfully addressed the issue of empty pixels. The proposed method can effectively meet the accurate panoramic imaging requirements for complex surroundings with varied object-distance information.
... Using the reprojection matrix obtained by binocular correction calibration, the following formula is used to calculate the coordinates in the camera coordinate system [11]: ...
In recent years, with the continuous development of computer vision and artificial intelligence technology, gesture recognition is widely used in many fields, such as virtual reality, augmented reality and so on. However, the traditional binocular camera architecture is limited by its limited field of view Angle and depth perception range. Fisheye camera is gradually applied in gesture recognition field because of its advantage of larger field of view Angle. Fisheye cameras offer a wider field of vision than previous binocular cameras, allowing for a greater range of gesture recognition. This gives fisheye cameras a distinct advantage in situations that require a wide field of view. However, because the imaging mode of fisheye camera is different from traditional camera, the image of fisheye camera has a certain degree of distortion, which makes the calculation of gesture recognition more complicated. Our goal is to design a distortion correction processing strategy suitable for fisheye cameras in order to extend the range of gesture recognition and achieve large field of view gesture recognition. Combined with binocular technology, we can use the acquired hand depth information to enrich the means of interaction. By taking advantage of the large viewing Angle of the fisheye camera to expand the range of gesture recognition, make it more extensive and accurate. This will help improve the real-time and precision of gesture recognition, which has important implications for artificial intelligence, virtual reality and augmented reality.
... The former can affect the results of the inspection, and the latter can increase the computational cost of defect detection. The collected real images of the bottle cap need to be spliced into a two-dimensional plane 360° panoramic view, which can be completed by using image stitching technology [3,4]. Image stitching technology is the registration and fusion of several adjacent images or photos with overlapping areas to form a 360° or wideview panoramic image. ...
In the beverage, food and drug industry, more and more machine vision systems are being used for the defect detection of Polyethylene Terephthalate (PET) bottle caps. In this paper, in order to address the result of cylindrical distortions that influence the subsequent defect detection in the imaging process, a very fast image stitching algorithm is proposed to generate a panorama planar image of the surface of PET bottle caps. Firstly, the three-dimensional model of the bottle cap is established. Secondly, the relative poses among the four cameras and the bottle cap in the three-dimensional space are calculated to obtain the mapping relationship between three-dimensional points on the side surface of the bottle cap and image pixels taken by the camera. Finally, the side images of the bottle cap are unfolded and stitched to generate a planar image. The experimental results demonstrate that the proposed algorithm unfolds the side images of the bottle cap correctly and very fast. The average unfolding and stitching time for 1.6-megapixel color caps image can reach almost 123.6 ms.
... Due to the wide availability of consumer-level panoramic video capturing and imaging devices, panoramic images are widely used in many fields [1][2][3][4][5][6]. For example, they are used in 360-degree object tracking [1,4], equirectangular super-resolution [3], privacy protection in Google Street View [5] and roadway inventory management about traffic signs [6]. ...
Panoramic images have a wide range of applications in many fields with their ability to perceive all-round information. Object detection based on panoramic images has certain advantages in terms of environment perception due to the characteristics of panoramic images, e.g., lager perspective. In recent years, deep learning methods have achieved remarkable results in image classification and object detection. Their performance depends on the large amount of training data. Therefore, a good training dataset is a prerequisite for the methods to achieve better recognition results. Then, we construct a benchmark named Pano-RSOD for panoramic road scene object detection. Pano-RSOD contains vehicles, pedestrians, traffic signs and guiding arrows. The objects of Pano-RSOD are labelled by bounding boxes in the images. Different from traditional object detection datasets, Pano-RSOD contains more objects in a panoramic image, and the high-resolution images have 360-degree environmental perception, more annotations, more small objects and diverse road scenes. The state-of-the-art deep learning algorithms are trained on Pano-RSOD for object detection, which demonstrates that Pano-RSOD is a useful benchmark, and it provides a better panoramic image training dataset for object detection tasks, especially for small and deformed objects.
... In Ref. 7, a multicameras system is employed to collect all images around a considered position (except bottom and top sides), then with the stitching technology they get the whole panoramic image. Lin et al. 7 have proposed a model and an algorithm to limit camera distortion and stitching traces to have a good panoramic visual effect. This solution is used to have a wide FOV and to correct the fisheye lens distortion by projecting the captured image onto the cylindrical coordinate system. ...
The 360-deg or virtual reality video can capture all sides around the observer at the same time and provides the freedom to select any part of the surroundings for display using a head mounted display in the case of a single user or smart TV, curved screen, and even with video projectors placed in a 360-deg projection room in the case of multiusers. In order to encode these spherical videos with standard codecs, a projection step is necessary to transform the original 3-D space scene into a regular 2-D video sequence. Thus different geometric shapes can be used as equirectangular projection (ERP), cubemap projection (CMP), segmented sphere projection (SSP), etc. The proposed model presents the 360-deg video on eight square faces, six faces for the equatorial part, and two faces for the top and bottom views. This shape can ensure a better projection of the video thanks to the size ratio of the lateral faces, which is very close to the size ratio of televisions and video projectors used in 360-deg rooms. Quality metrics comparison shows average gains when compared with ERP and SSP models and the encoding time is hugely reduced when compared with CMP model.
... Görüntü mozaikleme yöntemi sayesinde aynı alana ait daha yakından alınan görüntüler ile yüksek çözünürlüklü görüntüler elde etmek mümkün olmaktadır. Alınan bu görüntüler düz bir biçimde birbirine eklenebileceği gibi panoramik görüntü elde etmede de kullanılabilirler [4]. ...
... Ġlk önce lensten gelen bozulmaları gidermek için geriye dönük bölünme, sonra tutarlılığı sağlamak için silindirik izdüĢümü yönteminden yararlanmıĢtır. Özellik tespiti için ölçekten bağımsız özellik dönüĢüm yöntemi (SIFT) ve yanlıĢ eĢleĢtirmeleri elemine etmek için rastgele örneklerin fikir birliği (RANSAC) algoritmalarını kullanmıĢtır [4]. Elibol su altında alınan görüntülerin mozaiklenmesi iĢlemi için alt haritalama yöntemlerinden yararlanmıĢtır. ...
